Early Forest Fire Detection Research Articles

Pyramid Attention Based Early Forest Fire Detection Using UAV Imagery

Early forest fire detection using unmanned aerial vehicle (UAV) imagery is widely implemented in recent years. However, as the size of moving object in UAV imagery changes dramatically, the issues of focusing more informative areas of an image, large-scale variation as well as temporal consistency preservation have yet to be resolved due to the wide field of vision of UAVs in flight. To address these issues, in this work, we concerned the visual characteristics of early stage forest fire in UAV imagery and employ pyramid attention mechanism. We engineered a novel convolutional neural network (CNN) based on the state-of-the-art backbone by stacking our proposed PyrAtten blocks. We built a large dataset of early stage forest fire, including real world aerial photographs shot using our UAV prototype. Extensive evaluation of PyrAtten demonstrates its efficiency and effectiveness in detecting multi-scale objects of fire and smoke in UAV imagery, even if the object takes up a very small proportion of the whole image. Compared with existing similarly-sized networks, average detecting accuracy of PyrAtten-ResNet-50 reaches 97.5%, with negligible increase in computational overhead.

A Lightweight Hierarchical AI Model for UAV-Enabled Edge Computing with Forest-Fire Detection Use-Case

As the unmanned aerial vehicles (UAVs) continue to be deployed for various mission-critical data acquisition, localized computing on the drone-acquired data for efficient analysis, without significantly impacting the limited resources on board the drone, has emerged as a formidable research challenge. In this article, we address this issue with a natural resource management use-case whereby early forest-fire detection using the popular convolutional neural network (CNN)-based inference models are considered in the drone. This can lead to resource exhaustion. To alleviate this, we propose a lightweight hierarchical artificial intelligence (AI) framework, which adaptively switches between a simple machine learning-based model and an advanced deep learning-based CNN model. Then, we formulate a multi-objective optimization problem to model the trade-off between forest-fire detection accuracy and computational performance. We obtain the Pareto-optimal solution of the formulated problem by optimizing a new hyperparameter (i.e., the confidence score threshold) by employing the technique for order of preference by similarity to ideal solution (TOPSIS) for the whole model. Thus, we alleviate the computational burden while retaining a high level of detection accuracy. Finally, based on a real dataset, empirical results are reported to evaluate the performance of our proposal in terms of its lightweight features.

Camera-based wildfire smoke detection for foggy environments

Smoke is the first visible sign of forest fires and the most commonly used feature for early forest fire detection using data from cameras. However, one of the natural challenges is the dense fog that appears in forests, which decreases the detection accuracy or triggers false alarms. In this study, we propose a system with a deep neural network-based image preprocessing approach that significantly improves the smoke segmentation and classification performance by dehazing the camera view. Our experimental results provide that the classification models reach 99% F1 score for the correct classification of smoke when the image dehazing method is used before the training process. The smoke localization system achieves 60% average precision when the mask region-based convolutional neural network is used with the ResNet101-FPN backbone. The proposed approach can be utilized for all smoke segmentation frameworks to increase fire detection performance.

FFireNet: Deep Learning Based Forest Fire Classification and Detection in Smart Cities

Forests are a vital natural resource that directly influences the ecosystem. Recently, forest fire has been a serious issue due to natural and man-made climate effects. For early forest fire detection, an artificial intelligence-based forest fire detection method in smart city application is presented to avoid major disasters. This research presents a review of the vision-based forest fire localization and classification methods. Furthermore, this work makes use of the forest fire detection dataset, which solves the classification problem of discriminating fire and no-fire images. This work proposes a deep learning method named FFireNet, by leveraging the pre-trained convolutional base of the MobileNetV2 model and adding fully connected layers to solve the new task, that is, the forest fire recognition problem, which helps in classifying images as forest fires based on extracted features which are symmetrical. The performance of the proposed solution for classifying fire and no-fire was evaluated using different performance metrics and compared with other CNN models. The results show that the proposed approach achieves 98.42% accuracy, 1.58% error rate, 99.47% recall, and 97.42% precision in classifying the fire and no-fire images. The outcomes of the proposed approach are promising for the forest fire classification problem considering the unique forest fire detection dataset.

Bio-Inspirations - Melanophila Acuminata can Sense and Detect Forest Fires

Abstract: Forest-fires are caused due to various factors including natural ones, such as hot lightning striking the ignitable trees, and human ones such as negligent use of fire or fire-causing products like cigarettes and explosives, disruptive machinery deployed within the forest, etc. The spread of these fires, however, is largely determined by parameters such as temperature, wind, relative humidity, and rain; unsurprisingly, the most prominent of these factors is the temperature. Detection of anomalies in the temperature can be a crucial indication towards the possibility of a fire, therefore enabling a potentially quicker response and minimising the loss of land and other resources, besides human life. A specific beetle called the Fire Beetle, or the melanophila acuminata, is known to have evolved with a collection of sensors which can detect IR radiation with remarkable sensitivity, even from long distances. These beetles can potentially sense the emergence of a fire from as long as a few miles away. Since early detection of forest-fires is a decisive step towards dealing with it, taking inspiration from melanophila acuminata can be a way of doing so.

FOREST FIRE DETECTION USING DEEP LEARNING

Early forest fire detection is of great importance to avoid the huge damage of forests caused by fires. Early fire detection focuses on smoke detection. The forest area is gradually decreased because of increasing forest fire and human activities. The satellite sensor is used to collect the forest thermal image in different places and analyze the data in these images to detect the fire region if they occur. Image processing technique can effectively predict the fire in the forest. The input image is pre- processed to enhance the image quality, because the input image has the noise, so the pre- processing technique is used to eliminate the noise in this system and enhance the image quality. The pre-processed image is taking to the segmentation process; it processes the image to adjacent the forest sub-area. In this system, the affected area is separately detected, and it gives the accurate forest fire in this system because the output image intensity is better to stabilize the average value of the image. In our proposed system we propose a deep learning method that uses a Convolutional Neural Network (CNN) to predict the forest fire detection. The convolutional layer is the main building block of the convolutional neural network. Usually, the layers of the network are fully connected in which a neuron in the next layer is connected to all the neurons in the previous layer. We are going to detect the fire in the forest result based on the accuracy which we get in train and test of the dataset based CNN algorithm using that we show the graph result. KEYWORDS CNN– Convolutional neural network.

Early Detection of Forest Fire Using Mixed Learning Techniques and UAV.

Over the last few decades, forest fires are increased due to deforestation and global warming. Many trees and animals in the forest are affected by forest fires. Technology can be efficiently utilized to solve this problem. Forest fire detection is inevitable for forest fire management. The purpose of this work is to propose deep learning techniques to predict forest fires, which would be cost-effective. The mixed learning technique is composed of YOLOv4 tiny and LiDAR techniques. Unmanned aerial vehicles (UAVs) are promising options to patrol the forest by making them fly over the region. The proposed model deployed on an onboard UAV has achieved 1.24 seconds of classification time with an accuracy of 91% and an F1 score of 0.91. The onboard CPU is able to make a 3D model of the forest fire region and can transmit the data in real time to the ground station. The proposed model is trained on both dense and rainforests in detecting and predicting the chances of fire. The proposed model outperforms the traditional methods such as Bayesian classifiers, random forest, and support vector machines.

Increase the WSN-Lifespan Used in Monitoring Forest Fires by PSO

The Wireless Sensor Networks (WSNs) have become the most cost-effective monitoring solution due to their low cost, despite their major drawback of limited power due to dependence on batteries. Clustering is one of the successful solutions for extending the life of the WSN. Where optimal CH selection results in an increase in the lifetime of WSN. The paper discusses a strategy for field deployment of nodes in the form of clusters and a method for Cluster Head (CH) selection using Particle Swarm Optimization (PSO). The method employs a fitness function to select the optimum CHs for cluster nodes. This paper simulates a case study for the early detection of forest fires and demonstrates how to extend the lifetime of a WSN by utilizing the proposed PSO algorithm.

A Forest Fire Recognition Method Using UAV Images Based on Transfer Learning

Timely detection of forest wildfires is of great significance to the early prevention and control of large-scale forest fires. Unmanned Aerial Vehicle(UAV) with cameras has the characteristics of wide monitoring range and strong flexibility, making it very suitable for early detection of forest fire. However, the visual angle/distance of UAV in the process of image sampling and the limited sample size of UAV labeled images limit the accuracy of forest fire recognition based on UAV images. This paper proposes a FT-ResNet50 model based on transfer learning. The model migrates the ResNet network trained on an ImageNet dataset and its initialization parameters into the target dataset of forest fire identification based on UAV images. Combined with the characteristics of the target data set, Adam and Mish functions are used to fine tune the three convolution blocks of ResNet, and focal loss function and network structure parameters are added to optimize the ResNet network, to extract more effectively deep semantic information from fire images. The experimental results show that compared with baseline models, FT-ResNet50 achieved better accuracy in forest fire identification. The recognition accuracy of the FT-ResNet50 model was 79.48%; 3.87% higher than ResNet50 and 6.22% higher than VGG16.

Geospatial Artificial Intelligence for Early Detection of Forest and Land Fires

Over the years, early detection of forest and land fires has been conducted using hotspot data provided by the National Institute of Aeronautics and Space (LAPAN), based on its interpretation of satellite images. The hotspot data have tremendously helped firefighting efforts and further enforcement. However, the system has several shortcomings, especially due to its inability to distinguish forest and land fires from other hot surfaces or fires caused by common human activities. Furthermore, this method also requires labor-intensive verification, and heavily relies on human factors for advanced analysis and validation. Recently, the DG of Law Enforcement of the Ministry of Environment and Forestry (DGLE MoEF) has been piloting a new approach through advancement in artificial intelligence, called Geospatial Artificial Intelligence (GeoAI). By utilizing recorded satellite image data from 2017 - 2019, the machine has been trained to recognize the pattern and tone of the image in burnt areas so that it can validate the presence of the burnt area based on the history of Sentinel-2 imagery for the past week at each cluster. DGLE MoEF found that the burnt area data processed by GeoAI has better accuracy than the hotspot count for forest and land fire identification. Moreover, GeoAI may ease forest and land fire analysis and verification by automatically overlaying forest area and company concessions at the burnt area. GeoAI’s innovation in forest and land fire monitoring can produce more accurate and complete early detection data of forest and land fires than currently available hotspot data. The results of hotspot clustering that detect fires may assist firefighters in rapidly extinguishing the fire, and support law enforcement officers in determining the appropriate target location. Therefore, GeoAI technology may increase the effectiveness and efficiency of resources allocated by law enforcement officers in providing better and more responsive public services.
 Keywords: GeoAI, geospatial technology, artificial intelligence, forest fire, hotspot

DeepFire: A Novel Dataset and Deep Transfer Learning Benchmark for Forest Fire Detection

Forest fires pose a potential threat to the ecological and environmental systems and natural resources, impacting human lives. However, automated surveillance system for early forest fire detection can mitigate such calamities and protect the environment. Therefore, we propose a UAV-based forest fire fighting system with integrated artificial intelligence (AI) capabilities for continuous forest surveillance and fire detection. The major contributions of the proposed research are fourfold. Firstly, we explain the detailed working mechanism along with the key steps involved in executing the UAV-based forest fire fighting system. Besides, a robust forest fire detection system requires precise and efficient classification of forest fire imagery against no-fire. Moreover, we have curated a novel dataset (DeepFire) containing diversified real-world forest imagery with and without fire to assist future research in this domain. The DeepFire dataset consists of 1900 colored images with 950 each for fire and no-fire classes. Next, we investigate the performance of various supervised machine learning classifiers for the binary classification problem of detecting forest fire. Furthermore, we propose a VGG19-based transfer learning solution to achieve improved prediction accuracy. We assess and compare the performance of several machine learning approaches such as k -nearest neighbors, random forest, naive Bayes, support vector machine, logistic regression, and the proposed approach for accurately identifying fire and no-fire images in the DeepFire dataset. The simulation results demonstrate the efficacy of the proposed approach in terms of accurate classification, where it achieves the mean accuracy of 95% with 95.7% precision and 94.2% recall.

Prototype of Fire Detection Tool Using Short Message Service (SMS) Notification as A Disaster Mitigation Effort Against Environmental Damage Due to Forest Fires

In relation to the threat of drought, it is necessary to do a drought analysis to evaluate the drought that has occurred. Another disaster caused by water drought is forest fires. The purpose of this study using the prototype of a Forest Fire Detection Tool (FFDT) are to early detection of forest fires and providing Short Message Service (SMS) notification of forest fires to the officer. The method of this study used a prototype of a FFDT with SMS Notification. This tool is controlled using the ATmega328 microcontroller or better known as Arduino Uno R3 and also the GSM 800L v2 module so that this tool will provide notification to forest guards in the form of sirens and SMS sounds when there are indications of smoke or fire that are identical to the event of a forest fire. Monitoring uses fire sensors, namely fire for the detection of flames that are often associated with forest fires and uses sensors as soon as possible, namely MQ2 and MQ9, all of which are equipped in one device, a forest fire detector using the Arduino Mega microcontroller. When there is a good sign that the flame or as soon as possible is read, the tool will send an SMS notification to the forest officer, the process of sending the SMS makes the fire process can detect even though it is still in a small condition or not widened.

Forest fire detection system using barrier coverage in wireless sensor networks

Forest fires are one of the main reasons for various types of pollution and disturb an ecology in a very impactful way. Technological applications to detect, monitor, and avoid forest fires have helped reduce the damage caused by these fires but are not effective in many situations. Wireless sensor networks have played a crucial role in many of these methods. Barrier coverage-based sensor networks are the solution. This paper puts forth a system that helps in the early detection of forest fires and helps authorities to get into action to avoid them as soon as possible. Sensor nodes in this system are drones that hover over the area under surveillance. These drones are equipped with the necessary setup to detect forest fires and to transfer data to other nodes so that the information reaches the appropriate authorities. These drones form a set of barriers so that fire starting at any point in the area is detected. A base station is considered as the final destination of data and communication is done through the X-bee module protocol. Data is hopped from one node to another until it reaches the base station.

IoT-based early forest fire detection using MLP and AROC method

IoT-based early forest fire detection using MLP and AROC method

IoT-based early forest fire detection using MLP and AROC method

IoT-based early forest fire detection using MLP and AROC method

Design and Development of an Intelligent System Based on the Internet of Things for the Early Detection of Forest Fires

Automatic environmental monitoring is a field that encompasses several scientific practices for the assessment of risks that may negatively impact a given environment, such as the forest. A forest is a natural environment that hosts various forms of plant and animal life, so preserving the forest is a top priority. To this end, the authors of this paper will focus on the development of an intelligent system for the early detection of forest fires, based on an IoT solution. This latter will thus facilitate the exploitation of the functionalities offered by the Cloud and mobile applications. Detecting and predicting forest fires with accuracy is a difficult task that requires machine learning and an in-depth analysis of environmental conditions. This leads the authors to adopt the forward neural network algorithm by highlighting its contribution through real experiments, performed on the prototype developed in this paper.

Performance of fire hotspot detection system with sensor based on angle width and voltage difference monitoring for forest security

Fires that occur naturally in the forest can cause uncontrolled fires due to the rapid spread of heat. This research is focused on the observation land in the Puncak Besar area of Pacet in Pengalengan District, Indonesia, where the area of land burned is approximately 100 hectares. The early warning system that was built in this study uses a range widening method. This method consists of 1 sector that functions to detect heat and initial gas that occurs in the remote area. The initial area of the hotspot is usually not detected by the forest operator. After testing the sensor performance on this device, the fire sensor can detect hotspots with an average range of 440 cm. The width of the detection angle using a shield can reach a range of - 45° to 45° and the wide angle of detection of a fire without a shield can reach a range of -90° to 90°. While the communication system on this device uses the GPRS/GSM module to send data to the Android application as a monitoring system. By using this early forest fire detection system, forest operators can monitor the starting point of a fire in remote areas around the forest and minimize the spread of fire points as one solution to overcome the wider spread of forest fires.

Improvement of forest fire monitoring system by expanding information and technological possibilities of modern quadcopters

The article proposes a solution to an important problem — the development of an information technology based on expanding the functionality of non-specialized unmanned aerial vehicles (drones) for early detection of forest fires. The proposed information technology is designed to increase the effectiveness of monitoring forest fires. Тhe existing level of information technology does not fully settle the issue of reliable fire protection of forests. Today, there is a contradiction between the high cost of developing high-tech fire-fighting equipment and lack of its efficiency. The elimination of this contradiction will be facilitated by the involvement of additional non-technical and technical resources in the information technology of early detection of forest fire hotspots. The results of the analysis of the use of modern drones prove that the involvement of unmanned aerial vehicles significantly increases the efficiency of many types of monitoring and they can successfully be used to solve the problems of early detection of forest fire hotspots. The results of experiments are presented, which were carried out both for a series of digital images and for video.

ForestResNet: A Deep Learning Algorithm for Forest Image Classification

Due to its large area and rugged terrain, the forest often fails to be detected in time and eventually causes severe losses[1]. Therefore, early detection of forest fires is significant for forest fire protection. The application of deep learning to the classification of smoke and fire in forest images can detect forest conditions more accurately. In this paper, a classification network, named ForestResNet, is proposed to efficiently detect forest conditions, which uses ResNet50[2] as a feature extraction network to achieve rapid and accurate extraction of image feature information. Experimental results show that the proposed network achieves excellent segmentation performance in terms of efficiency and accuracy.

WITHDRAWN: A retrospective on ASPires - An advanced system for the prevention and early detection of forest fires

Forest fires cause huge, constantly increasing material damage and immaterial costs to humans, the environment and property. The paper describes the design and a prototypical implementation of an open system (ASPires) for the prevention and early detection of forest fires (public information (ASPires Consortium, 2019), overview (Peinl et al., 2020 [2])). Collected data are sent to and stored within a Cloud based system and may be rapidly made available to or forwarded to Crisis Management Centers (CMC)s or other institutions or human users. Among others, the use of new sensor and mobile communication technologies, the use of drones, data storage and analysis in a cloud, and direct connection with authorities reduces reaction time and thereby damage. This also sustains biodiversity in remote areas with rare and endemic species of flora and fauna. The concept has been tested and proven in 3 national parks in South East Europe.